TITLE:
Statistical Models and Machine Learning in Predicting Childhood Obesity and Related Metabolic Disorders
AUTHORS:
Ruiqi Huo
KEYWORDS:
Childhood Obesity, Metabolic Disorders, Statistical Models, Machine Learning, Risk Prediction, Precision Prevention
JOURNAL NAME:
Journal of Biosciences and Medicines,
Vol.14 No.5,
May
29,
2026
ABSTRACT: Childhood obesity has emerged as a major global public health challenge, closely linked to a range of metabolic disorders and long-term adverse health outcomes. Early risk identification and precise stratification are critical for effective prevention and intervention. In recent years, driven by the rapid expansion of public health data and methodological advances, traditional regression models, longitudinal data analysis, structural equation modeling, and machine learning algorithms have been widely applied in the early prediction of childhood obesity. These approaches enable the effective integration of demographic, behavioral, environmental, and physiological indicators, thereby improving predictive accuracy and practical utility. This review summarizes the application of statistical models and machine learning algorithms in predicting childhood obesity and related metabolic disorders, covering model construction, predictor selection, performance evaluation, and real-world application. Furthermore, current limitations, research gaps, and future directions—including multi-omics integration, long-term cohort validation, and personalized intervention models—are discussed. This review aims to provide a theoretical reference for early warning, precision prevention, and health management of childhood obesity.